Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.4413. Min Act: -0.1700
Data Index: 1809442 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.4101. Min Act: -0.1700
Data Index: 1124011 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.4101. Min Act: -0.1700
Data Index: 4092992 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.3476. Min Act: -0.1700
Data Index: 4489955 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.2851. Min Act: -0.1700
Data Index: 5082486 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.2226. Min Act: -0.1700
Data Index: 8641969 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.2226. Min Act: -0.1700
Data Index: 4595491 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.1913. Min Act: -0.1700
Data Index: 2861443 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.1913. Min Act: -0.1700
Data Index: 1983292 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.1913. Min Act: -0.1700
Data Index: 7754627 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.1601. Min Act: -0.1700
Data Index: 4191225 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.1601. Min Act: -0.1700
Data Index: 417067 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.1601. Min Act: -0.1700
Data Index: 5685667 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.1288. Min Act: -0.1700
Data Index: 6558242 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.1288. Min Act: -0.1700
Data Index: 1807851 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.1288. Min Act: -0.1700
Data Index: 4185949 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.0976. Min Act: -0.1700
Data Index: 8786495 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.0976. Min Act: -0.1700
Data Index: 1073061 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.0663. Min Act: -0.1700
Data Index: 3152529 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4413. Min Range: -4.4413
Max Act: 4.0663. Min Act: -0.1700
Data Index: 2489014 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19